Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    words related to uprooting or removal

    oai_token-act-pair · gpt-3.5-turbo

    words related to significant disruptions or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Negative Logits
     Mystery
    -0.63
     Contin
    -0.62
     rhythm
    -0.56
     Faul
    -0.55
     crunch
    -0.55
     Min
    -0.55
    mia
    -0.55
     elastic
    -0.54
     intermedi
    -0.54
     Frequ
    -0.53
    POSITIVE LOGITS
    oted
    4.49
    oting
    2.98
    otes
    2.30
    OTE
    1.99
    ote
    1.75
    oter
    1.74
    oters
    1.72
    ots
    1.71
    otted
    1.40
    otation
    1.32
    Act Density 0.004%

    No Known Activations